A robust damaged fingerprint identification algorithm based on deep learning

PurposeBook sorting system is one of specific application in smart library scenarios, and it now has been widely used in most libraries based on RFID (radio-frequency identification devices) technology. Book identification processing is one of the core parts of a book sorting system, and the efficiency and accuracy of book identification are extremely critical to all libraries. In this paper, the authors propose a new image recognition method to identify books in libraries based on barcode decoding together with deep learning optical character recognition (OCR) and describe its application in library book identification processing.Design/methodology/approachThe identification process relies on recognition of the images or videos of the book cover moving on a conveyor belt. Barcode is printed on or attached to the surface of each book. Deep learning OCR program is applied to improve the accuracy of recognition, especially when the barcode is blurred or faded. The approach the authors proposed is robust with high accuracy and good performance, even though input pictures are not in high resolution and the book covers are not always vertical.FindingsThe proposed method with deep learning OCR achieves best accuracy in different vertical, skewed and blurred image conditions.Research limitations/implicationsMethods that the authors proposed need to cooperate and practice in different book sorting machine.Social implicationsThe authors collected more than 500 books from a library. These photos display the cover of more than 100 randomly picked books with backgrounds in different colors, each of which has about five different pictures captured from variety angles. The proposed method combines traditional barcode identification algorithm with the authors’ modification to locate and deskew the image. And deep learning OCR is involved to enhance the accuracy when the barcode is blurred or partly faded. Book sorting system design based on this method will also be introduced.Originality/valueExperiment demonstrates that the accuracy of the proposed method is high in real-time test and achieves good accuracy even when the barcode is blurred. Deep learning is very effective in analyzing image content, and a corresponding series of methods have been formed in video content understanding, which can be a greater advantage and play a role in the application scene of intelligent library.

Download Full-text

Design of Embedded Automated Fingerprint Identification System Based on DSP

Advanced Engineering Forum ◽

10.4028/www.scientific.net/aef.1.97 ◽

2011 ◽

Vol 1 ◽

pp. 97-101

Author(s):

Hong Sun

Keyword(s):

Embedded System ◽

Fingerprint Identification ◽

Identification System ◽

Identification Algorithm ◽

Research Topics ◽

Hardware System ◽

Serial Peripheral Interface ◽

The Embedded System ◽

Time And Space Complexity ◽

Selection Of

The automated fingerprint identification algorithm has high time and space complexity in the embedded system. How to reduce the complexity is one of the hot research topics. The process of fingerprint identification and choice of algorithm platform are analyzed in the paper. Design of embedded fingerprint identification hardware system based on DSP, including the selection of microprocessor and fingerprint sensor and the communication between them, is introduced in detail. In additional, main software composition and flow are explained. At last, serial peripheral interface communication is simulated.

Download Full-text

Evaluation of a Fingerprint Identification Algorithm with SIFT Features

2012 IIAI International Conference on Advanced Applied Informatics ◽

10.1109/iiai-aai.2012.34 ◽

2012 ◽

Cited By ~ 8

Author(s):

Ali Ismail Awad ◽

Kensuke Baba

Keyword(s):

Fingerprint Identification ◽

Identification Algorithm ◽

Sift Features

Download Full-text

Fingerprint Recognition in Wavelet Domain

Jurnal Teknologi ◽

10.11113/jt.v41.708 ◽

2012 ◽

Author(s):

Wan Azizun Wan Adnan ◽

Tze Siang Lim ◽

Salasiah Hitam

Keyword(s):

Image Processing ◽

Fourier Transform ◽

Fast Fourier Transform ◽

Low Cost ◽

Recognition System ◽

Fingerprint Recognition ◽

Fingerprint Identification ◽

Small Computer ◽

Identification System ◽

Identification Algorithm

Teknik cetak ibujari merupakan satu daripada teknologi biometrik yang paling boleh diharapkan. Beberapa pendekatan terhadap pemadanan ibujari secara automatik telah dicadangkan dalam saranan. Dalam pengecaman ibujari, pra–prosesan seperti pelicin, binarization dan thinning diperlukan. Kemudian, ciri–ciri cetak ibujari yang terperinci diambil berdasarkan algoritma pengecaman cetak ibujari (seperti dengan menggunakan Fast Fourier Transform (FFT)) mungkin memerlukan teknik–teknik pengkomputeran yang banyak sehingga menjadikannya tidak praktikal. Algoritma berdasarkan wavelet mungkin merupakan kunci untuk membina sistem pengecaman cetak ibujari kos rendah yang boleh dioperasi dalam sistem komputer bermodul kecil. Di sini, satu sistem pengecaman cetak ibujari yang boleh menjalankan pemadanan cetak ibujari berdasarkan kepada ciri–ciri yang diperolehi daripada domain jelmaan wavelet diperkenalkan. Kajian ini adalah berdasarkan kepada perisian MATLAB dan aplikasinya dalam toolbox seperti Wavelet and Image Processing Toolbox. Kata kunci: Biometrik, wavelet, cetaksekuriti, pengecaman cetak ibujari Fingerprint technique is one of the most reliable biometric technologies. In the fingerprint recognition, pre-processing such as smoothing, binarization, and thinning are needed. Then, fingerprint minutia feature is extracted. Some fingerprint identification algorithm (such as using Fast Fourier Transform, (FFT)) may require so much computation as to be impractical. Wavelet based algorithm may be the key to making a low cost fingerprint identification system that would operate on a small computer. We present a fingerprint recognition system that can match the fingerprint images based on features extracted in the wavelet transform domain. This study is implemented based on MATLAB Software and their toolbox applications, such as Wavelet and Image Processing Toolbox. Key words: Biometrics, wavelet, security, fingerprint recognition

Download Full-text

Improved Fingerprint Recognition Algorithm Application Study on Smart Home

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.734-737.2970 ◽

2013 ◽

Vol 734-737 ◽

pp. 2970-2973

Author(s):

Shu Qian Chen ◽

Yang Lie Fu ◽

Ming Yang Yin

Keyword(s):

Smart Home ◽

Recognition Rate ◽

Weight Coefficient ◽

Fingerprint Recognition ◽

Fingerprint Identification ◽

Point Pattern ◽

Identification System ◽

Identification Algorithm ◽

Matching Algorithm ◽

Improved Algorithm

Study on a new type of fingerprint identification algorithm and its application in intelligent home electric control lock problem. The traditional fingerprint recognition algorithms on fingerprint minutiae matching accuracy is low, difficult to accurately extract details, leading to lock malfunction or could not be opened. In order to overcome this problem, improved Point pattern fingerprint recognition matching algorithm, joined the matching weight coefficient on the base of pattern matching algorithm, and gives the hardware structure of fingerprint identification system, the improved algorithm is successfully applied in smart home applications, the example shows that, the improved algorithm can effectively improve the recognition rate , reduce false positives, has a certain practical value.

Download Full-text